⚖️ Alignment & RLHF¶

🧠 NeurIPS2026 · 2 paper notes

Authority Bias in Language Models: Source Deference and User Agreement Are Not Interchangeable: Holding the wrong answer fixed and changing its endorser, the paper uses direction removal and an independently fitted attribution patch to show selectively intervenable differences between wrong-source deference and user agreement in three open-weight families, so one sycophancy evaluation cannot substitute for the other.
Learning Where It Matters: Geometric Anchoring for Robust Preference Alignment: GAPO constructs an ephemeral geometric anchor near the current policy along the direction that decreases the batch-average preference margin, then reduces brittle pairs' update weights according to their margin degradation, improving multiple alignment evaluations and controlled noise experiments without winning every model–metric combination.